© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2714
    Prev
    Next
    INDEX
    Explanations

    fullwidth punctuation

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     med
    -20.25
    	lib
    -19.88
    (lib
    -19.75
    	register
    -18.38
     median
    -18.25
     Germ
    -18.25
     simulator
    -18.00
     OT
    -17.38
     ot
    -17.13
    Ber
    -17.00
    POSITIVE LOGITS
    �
    33.75
    乙方
    30.75
    乙
    30.38
     �
    28.38
    �
    28.13
    eth
    26.88
    丙
    25.38
     eth
    25.13
    甲方
    24.13
    Eth
    23.75
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.